一、模型初始化
1、创建模型并载入预训练参数
准备了数据集后，我们开始构建model，training网络结构上一节已经介绍完了，现在我们看一看训练时如何调用training结构的网络。
如上所示，我们首先建立图结构（详见上节『计算机视觉』Mask-RCNN_训练网络其二：train网络结构），然后选择初始化参数方案
例子（train_shape.ipynb）中使用的是COCO预训练模型，如果想要"Finds the last checkpoint file of the last trained model in the
model directory"，那么选择"last"选项。
载入参数方法如下，注意几个之前接触不多的操作，
- 载入h5文件使用模块为h5py
- keras model有属性.layers以list形式返回全部的层对象
-
keras.engine下的saving模块load_weights_from_hdf5_group_by_name按照名字对应，而load_weights_from_hdf5_group按照记录顺序对应
def load_weights(self, filepath, by_name=False, exclude=None):
"""Modified version of the corresponding Keras function with
the addition of multi-GPU support and the ability to exclude
some layers from loading.
exclude: list of layer names to exclude
"""
import h5py
# Conditional import to support versions of Keras before 2.2
# TODO: remove in about 6 months (end of 2018)
try:
from keras.engine import saving
except ImportError:
# Keras before 2.2 used the 'topology' namespace.
from keras.engine import topology as saving
if exclude:
by_name = True
if h5py is None:
raise ImportError('`load_weights` requires h5py.')
f = h5py.File(filepath, mode='r')
if 'layer_names' not in f.attrs and 'model_weights' in f:
f = f['model_weights']
# In multi-GPU training, we wrap the model. Get layers
# of the inner model because they have the weights.
keras_model = self.keras_model
layers = keras_model.inner_model.layers if hasattr(keras_model, "inner_model")\
else keras_model.layers
# Exclude some layers
if exclude:
layers = filter(lambda l: l.name not in exclude, layers)
if by_name:
saving.load_weights_from_hdf5_group_by_name(f, layers)
else:
saving.load_weights_from_hdf5_group(f, layers)
if hasattr(f, 'close'):
f.close()
# Update the log directory
self.set_log_dir(filepath)